Qwen: Qwen3.5 122B A10B
Chatbailian/qwen3.5-122b-a10bQwen3.5-122B-A10B is a hybrid-architecture vision-language model from Alibaba's Qwen3.5 series, combining linear attention with sparse MoE for efficient inference. With 122B total parameters and 10B active, it ranks just below Qwen3.5-397B in overall performance. Context: 256K tokens, output: 64K. Accessible via the OpenAI-compatible protocol.
Providers
/v1/chat/completionsCode Examples
from openai import OpenAIclient = OpenAI(base_url="https://api.ofox.io/v1",api_key="YOUR_OFOX_API_KEY",)response = client.chat.completions.create(model="bailian/qwen3.5-122b-a10b",messages=[{"role": "user", "content": "Hello!"}],)print(response.choices[0].message.content)
Benchmarks
Qwen: Qwen3.5 122B A10B scores 1417 in the Overall category of the LMArena text leaderboard (style control), ranking #102 of 374 models based on 28,530 human preference votes (updated 2026-07-12).
| Category | Arena Score | 95% CI | Rank | Votes |
|---|---|---|---|---|
| Overall | 1417 | 1413–1422 | #102 of 374 | 28,530 |
| Hard Prompts | 1433 | 1427–1438 | #108 of 374 | 17,859 |
| Coding | 1459 | 1452–1467 | #105 of 369 | 7,809 |
| Math | 1424 | 1410–1438 | #87 of 362 | 1,778 |
| Creative Writing | 1367 | 1357–1376 | #127 of 372 | 4,351 |
| Instruction Following | 1407 | 1400–1413 | #100 of 374 | 9,029 |
| Chinese | 1463 | 1448–1479 | #89 of 344 | 1,638 |
Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.